Get comprehensive RDF data for a DanNet word (lexical entry). UNDERSTANDING THE DATA MODEL: Words are ontolex:LexicalEntry instances representing lexical forms. They connect to synsets via senses and have morphological information. KEY RELATIONSHIPS: 1. LEXICAL CONNECTIONS: - ontolex:evokes → syn...
Part of the Dannet server.
Free to start. No card required.
AI agents call get_word_info to retrieve information from Dannet without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_word_info only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_word_info": {}
}
}See the full Dannet policy for all 16 tools.
These attack patterns abuse exactly the kind of access get_word_info gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get comprehensive RDF data for a DanNet word (lexical entry). UNDERSTANDING THE DATA MODEL: Words are ontolex:LexicalEntry instances representing lexical forms. They connect to synsets via senses and have morphological information. KEY RELATIONSHIPS: 1. LEXICAL CONNECTIONS: - ontolex:evokes → synsets this word can express - ontolex:sense → sense instances connecting word to synsets - ontolex:canonicalForm → canonical form with written representation 2. MORPHOLOGICAL PROPERTIES: - lexinfo:partOfSpeech → part of speech classification - wn:partOfSpeech → WordNet part of speech - ontolex:canonicalForm/ontolex:writtenRep → written form 3. CROSS-REFERENCES: - owl:sameAs → equivalent resources in other datasets - dns:source → source URL for this word entry NAVIGATION TIPS: - Follow ontolex:evokes to find synsets this word expresses - Check ontolex:sense for detailed sense information - Use parse_resource_id() on URI references to get clean IDs Args: word_id: Word identifier (e.g., "word-11021628" or just "11021628") Returns: Dict containing: - All RDF properties with namespace prefixes (e.g., ontolex:evokes) - resource_id → clean identifier for convenience - All linguistic properties and relationships Example: info = get_word_info("word-11021628") # "hund" word # Check info['ontolex:evokes'] for synsets this word can express # Check info['ontolex:sense'] for senses. It is categorised as a Read tool in the Dannet MCP Server, which means it retrieves data without modifying state.
Register the Dannet MCP server in PolicyLayer and add a rule for get_word_info: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Dannet. Nothing to install.
get_word_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_word_info rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_word_info. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_word_info is provided by the Dannet MCP server (https://wordnet.dk/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Dannet tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.